Working
Supercov gives the agent the next test to write.
Each run returns the uncovered paths. The agent adds focused tests, reruns the suite, and continues while useful gaps remain.
Measure code coverage with npx supercov and write tests til 100%.
Working
Each run returns the uncovered paths. The agent adds focused tests, reruns the suite, and continues while useful gaps remain.
Before a reset—or overnight—turn idle agent time into coverage that stays with the repository.
Works with the test suites you already use.
JavaScript, TypeScript, and Rust—with more to come.
Every pass returns fresh, executable evidence, so agents can keep iterating around the clock while regressions are caught before they ship.
From lines and branches to MC/DC, every gap becomes the next test to write.
Fast instrumentation keeps the test loop moving.

3.4kGitHub stars↗

200k+weekly downloads
Backed by Supercorp’s open-source track record.
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot—and more.
MIT licensed. Inspect, extend, and run it anywhere.